Control plane and data plane. Computing systems now. Glacial process of innovation made worse by standards process. Computing systems once upon a time

Size: px
Start display at page:

Download "Control plane and data plane. Computing systems now. Glacial process of innovation made worse by standards process. Computing systems once upon a time"

Transcription

1 Classical work Architecture A A A Intro to SDN A A Oerating A Secialized Packet A A Oerating Secialized Packet A A A Oerating A Secialized Packet A A Oerating A Secialized Packet Oerating Secialized Packet A A Oerating We have lost our way A Secialized Packet Routing, management, mobility management, access control, VPNs, Million of 5400 RFCs Barrier to entry lines of source code 500M gates 10Gbytes RAM Bloated Power Hungry Many comlex functions baked into the infrastructure OSPF, BGP, multicast, differentiated services, Traffic Engineering, NAT, firewalls, MPLS, redundant layers, An industry with a mainframe-mentality A A A Oerating Secialized Packet Reality A A A Oerating Secialized ized Packet Lack of cometition means glacial innovation Closed architecture means blurry, closed interfaces Vertically integrated, comlex, closed, rorietary Not suitable for exerimental ideas Not good for network owners & users Not good for researchers

2 Glacial rocess of innovation made worse by standards rocess Idea Standardize Wait 10 years Driven by vendors Consumers largely locked out Lowest common denominator features Glacial innovation Deloyment Wait x years Comuting systems once uon a time Vertically integrated systems Prorietary hardware Prorietary OS Prorietary alications Highly reliable Can you icture google, yahoo, facebook on such a latform? Slow software innovation Prorietary develoment Small industry Comuting systems now Control lane and data lane A A A A A A A A A A A Windows (OS) Oen Interface or Linux Oen Interface Microrocessor or Mac OS Microrocessor Oen interfaces Fast innovation o Everyone can articiate Hugh industry Software is now art of everything. Control lane of a network The functions of a network that control the behavior of the network E.g.: Which ath to take for a acket? Which ort to forward a acket? Should the acket be droed? Control lane functions are tyically realized by software such as routing rotocols, firewall code, etc. Data lane of a network The functions of a network that actually forward or dro ackets. Data lane functions are tyically realized by hardware Control lane and data lane are vertically integrated in traditional networking equiment Searating software from hardware searating control lane from data lane.

3 Conventional networking system today (before SDN) Ideal networking system for innovation Custom hardware OS Bundled alications Mainframe mindset: software for the control lane cannot be searated from the forwarding hardware in the data lane. o Vertically integrated, comlex, closed, rorietary o Innovation is only ossible if one has access to the router box. No significant innovation in the ast 40 years. A A A A A A A A A A A Windows or Oen Interface Linux or Oen Interface Mac OS work as API of OS work Oerating s API for controlling work hardware work hardware Ideal networking system for innovation SDN now: searate forwarding hardware from controlling software A A A A A A A A A A A Windows or Oen Interface Linux or Oen Interface Mac OS Searate hardware from software Standardize the interface Each layer rovides an abstraction Innovation is ossible for anyone just like software develoment for a comuting system. This is the vision of SDN/OenFlow. A A A A A A A A A A A Windows or Oen Interface Linux or Oen Interface Mac OS 4. Firewall, virtual network, TE, etc Northbound API, not standardized yet 3. SDN controllers (floodlight, nox, etc) 1. OenFlow: standardized for ernet// 2. OenFlow enabled switches/routers simle hardware doing forwarding only forwarding table can be set by other entity through OenFlow

4 A Classical work Architecture The Software-defined work A A A work Oerating A A A A A A A Oerating A Secialized Packet A A Oerating Secialized Packet A A A Oerating A Secialized Packet A A Oerating A Secialized Packet A A Oerating A Secialized Packet A A Oerating Secialized Packet A A A Oerating A Secialized Packet A A Oerating A Secialized Packet Oerating Secialized Packet Oerating Secialized Packet The Software-defined work 3. Well-defined oen API 2. At least one good oerating syst Extensible, ossibly oen-sourc A A A Software-Defined work with key Abstractions in the Control Plane work Oerating Simle Packet 1. Oen interface to hardware Simle Packet Simle Packet Simle Packet Simle Packet

5 Isolated slices A A work Oerating 1 A A work Oerating 2 A A work Oerating 3 A Oen interface to hardware Virtualization or Slicing Layer Simle Packet Simle Packet Many oerating systems, or Many versions A work Oerating 4 Oen interface to hardware Simle Packet Simle Packet What and Why software defined? Software defined becomes very oular words Software defined networking, software defined storage, software defined radio, etc. What is it? Underlying system feature is exosed to the uer layer alication develoer through an API. functionality is imlemented over the API as an a. Another word for Software defined is Programmable. Simle Packet What is software defined networking? Abstraction Software-defined networking (SDN) is an aroach to comuter networking that allows network administrators to manage network services through abstraction of lower-level functionality. Abstractions for three roblems: Constrained forwarding model, distributed state, detailed configuration SDN is Directly rogrammable: network control is rogrammable because it is decouled from forwarding functions Agile: administrator can dynamically adjust network-wide traffic flow to meet changing needs. Centrally managed: network intelligence is logically centralized. Programmatically configured Oen standards-based and vendor-neutral Purose: Abstract away forwarding hardware Flexible Behavior secified by control lane Built from basic set of forwarding rimitives Minimal Streamlined for seed and low-ower Control rogram not vendor-secific OenFlow is an examle of such an abstraction

6 State Distribution Abstraction Configuration abstraction Shield control mechanisms from state distribution while allowing access to the state Slit global consensus-based distributed algorithms into two indeendent comonents: a distributed (database) system and a centralized algorithm. We know how to deal with both. Natural abstraction: global network view Imlemented with a network oerating system. Control (configuration) mechanism is now abstracted as a function of the global view using API Control is now based on a centralized grah algorithm instead of a distributed rotocol. Alication should not configure each individual network device. The NOS rovide consistent global view of the network Configuration is a function of the global view NOS eases the imlementation of functionality Does not hel secification of functionality Need a secification abstraction Consequences Contrast between SDN and conventional network More innovation in network services Owners, oerators, 3 rd arty develoers, researchers can imrove the network E.g. energy management, data center management, olicy routing, access control, denial of service, mobility Lower barrier to entry for cometition Healthier market lace, new layers SDN Controller may not be in the same box as the forwarding hardware Centralized routing algorithm with logically global view work functions are realized with a global view New abstraction must be develoed for the centralized view Conventional hardware and its control are in the same box Distributed routing algorithm work functions must be realized in a distributed manner, error-rone work abstraction is embedded in the distributed algorithms

7 Traditional network node: Router Router can be artitioned into control and data lane Management lane/ configuration Control lane / Decision: OSPF (Oen Shortest Path First) Data lane / Traditional network node: Tyical working Software Management lane Control Plane The brain/decision maker Data Plane Packet forwarder Control Program OenFlow Basics Control rogram oerates on view of network Inut: global network view (grah/database) Outut: configuration of each network device Control rogram is not a distributed system Abstraction hides details of distributed state Control Program A Control Program B work OS OenFlow Protocol ernet Control Path OenFlow Data Path ()

8 OenFlow: a ragmatic comromise OenFlow Basics + Seed, scale, fidelity of vendor hardware + Flexibility and control of software and simulation Vendors don t need to exose imlementation Leverages hardware inside most switches today (ACL tables) Control Program A Control Program B work OS If header =, send to ort 4 Packet If header =q, overwrite header with r, add header s, and send to orts 5,6 If header =?, send to me Flow Packet Table( s) Packet Primitives <Match, > Flow Table Flow table in switches, routers, and chisets Match arbitrary bits in headers: Header Match: 1000x01xx x Data Flow 1. Flow 2. Rule (exact & wildcard) Rule (exact & wildcard) Statistics Statistics Match on any header, or new header Allows any flow granularity Forward to ort(s), dro, send to controller Overwrite header with mask, ush or o Forward at secific bit-rate Flow 3. Flow N. Rule (exact & wildcard) Rule (exact & wildcard) Default Statistics Statistics 31

9 Flow Entry A flow entry consists of In Match fields Match against ackets Modify the action set or ieline rocessing Stats Match Udate the matching ackets Fields Stats Tye 1. Forward acket to ort(s) 2. Encasulate and forward to controller 3. Dro acket 4. Send to normal rocessing ieline Vlan Id Tos Proto Layer 2 Layer 3 Layer 4 1. Packet 2. Byte counters OenFlow Controller OenFlow Protocol (SSL/) Control Path OenFlow Data Path () Oen Flow Protocol Messages Controller-to-switch: from the controller to manage or insect the switch state Features, config, modify state, read state, acket-out, etc Asynchronous: send from switch without controller soliciting Packet-in, flow removed/exired, ort status, error, etc Symmetric: symmetric messages without solicitation in either direction Hello, Echo, etc. Oenflow An Oenflow switch (ernet switch) has an internal flow table. If a acket matches an entry in the flow table, erform the actions (e.g. forward to ort 10) according to the flow table. If a acket does not match any entry in the flow table. Send it to the Oenflow controller The controller will figure out what to do with such acket The controller will then resond to the switch, informing how to handle such a acket so that the switch would know how to deal with such ackets next time. For each flow, ideally the controller will be queried once. Oenflow defines the standard interface to add and remove flow entries in the table.

10 OenFlow Examle Controller Flow switching and routing Software Layer OenFlow Client PC Layer 4 Layer Flow Table sort dort * * * * * ort 1 ort 1 ort 2 ort 3 ort 4 Each individual field + meta data Wild Card aggregation E.g. -subnet: */ OenFlow Basics Flow Table Entries Rule Stats Packet + byte counters 1. Forward acket to zero or more orts 2. Encasulate and forward to controller 3. Send to normal rocessing ieline 4. Modify Fields 5. Any extensions you add! ing * tye Examles ID Prot sort dort * 00:1f:.. * * * * * * * ort6 Flow ing ort3 Firewall tye ID Prot sort dort 00: :1f vlan ort6 ID c tye ToS Prot L4 sort L4 dort tye ID Prot sort dort + mask what fields to match * * * * * * * * * 22 dro 40

11 Routing * tye Examles ID Prot sort dort * * * * * * * * ort6 ing * tye ID Prot sort * 00:1f.. * vlan1 * * * * * dort ort6, ort7, ort9 Centralized vs Distributed Control Both models are ossible with OenFlow Centralized Control OenFlow OenFlow Controller Distributed Control Controller OenFlow OenFlow Controller Controller OenFlow OenFlow 41 Flow Routing vs. Aggregation Both models are ossible with OenFlow Reactive vs. Proactive (re-oulated) Both models are ossible with OenFlow Flow-Based Aggregated Reactive Proactive Every flow is individually set u by controller Exact-match flow entries Flow table contains one entry er flow Good for fine grain control, e.g. camus networks One flow entry covers large grous of flows Wildcard flow entries Flow table contains one entry er category of flows Good for large number of flows, e.g. backbone First acket of flow triggers controller to insert flow entries Efficient use of flow table Every flow incurs small additional flow setu time If control connection lost, switch has limited utility Controller re-oulates flow table in switch Zero additional flow setu time Loss of control connection does not disrut traffic Essentially requires aggregated (wildcard) rules

12 Going further Oenflow is imlemented in Mini (mininet.org) Related resources Oen working Foundation: htts:// This lecture materials are based on various resources in the net, in articular this file htts:// df And book Software Defined works A Comrehensive Aroach by Paul Goransson and Chuck Black

Software Defined Networks and OpenFlow. Courtesy of: AT&T Tech Talks.

Software Defined Networks and OpenFlow. Courtesy of: AT&T Tech Talks. MOBILE COMMUNICATION AND INTERNET TECHNOLOGIES Software Defined Networks and Courtesy of: AT&T Tech Talks http://web.uettaxila.edu.pk/cms/2017/spr2017/temcitms/ MODULE OVERVIEW Motivation behind Software

More information

Software-Defined Networking (SDN) Overview

Software-Defined Networking (SDN) Overview Reti di Telecomunicazione a.y. 2015-2016 Software-Defined Networking (SDN) Overview Ing. Luca Davoli Ph.D. Student Network Security (NetSec) Laboratory davoli@ce.unipr.it Luca Davoli davoli@ce.unipr.it

More information

Software Defined Networks and OpenFlow

Software Defined Networks and OpenFlow Tecnologie e Protocolli per Internet 1 Prof. Stefano Salsano e-mail: stefano.salsano@uniroma2.it AA2012/13 Blocco 5 v1 1 Software Defined Networks and OpenFlow 2 Acknowledgements Next slides are taken

More information

Comparing IS-IS and OSPF

Comparing IS-IS and OSPF Comaring IS-IS and OSPF ISP Workshos These materials are licensed under the Creative Commons Attribution-NonCommercial 4.0 International license (htt://creativecommons.org/licenses/by-nc/4.0/) Last udated

More information

Comparing IS-IS and OSPF

Comparing IS-IS and OSPF Comaring IS-IS and OSPF ISP Workshos Last udated 8 th Setember 2016 1 Comaring IS-IS and OSPF Both are Link State Routing Protocols using the Dijkstra SPF Algorithm So what s the difference then? And why

More information

Gerência SDN. Baseado em slides do Nick McKeown e Survey disponível em:

Gerência SDN. Baseado em slides do Nick McKeown e Survey disponível em: Gerência SDN Baseado em slides do Nick McKeown e Survey disponível em: http://arxiv.org/abs/1406.0440 What are Software Defined Networks? App App App App App App App App App App App Specialized Applications

More information

10 File System Mass Storage Structure Mass Storage Systems Mass Storage Structure Mass Storage Structure FILE SYSTEM 1

10 File System Mass Storage Structure Mass Storage Systems Mass Storage Structure Mass Storage Structure FILE SYSTEM 1 10 File System 1 We will examine this chater in three subtitles: Mass Storage Systems OERATING SYSTEMS FILE SYSTEM 1 File System Interface File System Imlementation 10.1.1 Mass Storage Structure 3 2 10.1

More information

AUTOMATIC GENERATION OF HIGH THROUGHPUT ENERGY EFFICIENT STREAMING ARCHITECTURES FOR ARBITRARY FIXED PERMUTATIONS. Ren Chen and Viktor K.

AUTOMATIC GENERATION OF HIGH THROUGHPUT ENERGY EFFICIENT STREAMING ARCHITECTURES FOR ARBITRARY FIXED PERMUTATIONS. Ren Chen and Viktor K. inuts er clock cycle Streaming ermutation oututs er clock cycle AUTOMATIC GENERATION OF HIGH THROUGHPUT ENERGY EFFICIENT STREAMING ARCHITECTURES FOR ARBITRARY FIXED PERMUTATIONS Ren Chen and Viktor K.

More information

Software Defined Networking

Software Defined Networking CSE343/443 Lehigh University Fall 2015 Software Defined Networking Presenter: Yinzhi Cao Lehigh University Acknowledgement Many materials are borrowed from the following links: https://www.cs.duke.edu/courses/spring13/compsc

More information

A Reconfigurable Architecture for Quad MAC VLIW DSP

A Reconfigurable Architecture for Quad MAC VLIW DSP A Reconfigurable Architecture for Quad MAC VLIW DSP Sangwook Kim, Sungchul Yoon, Jaeseuk Oh, Sungho Kang Det. of Electrical & Electronic Engineering, Yonsei University 132 Shinchon-Dong, Seodaemoon-Gu,

More information

36. I/O Devices. Operating System: Three Easy Pieces 1

36. I/O Devices. Operating System: Three Easy Pieces 1 36. I/O Devices Oerating System: Three Easy Pieces AOS@UC 1 I/O Devices I/O is critical to comuter system to interact with systems. Issue : w How should I/O be integrated into systems? w What are the general

More information

CS 4226: Internet Architecture

CS 4226: Internet Architecture Software Defined Networking Richard T. B. Ma School of Computing National University of Singapore Material from: Scott Shenker (UC Berkeley), Nick McKeown (Stanford), Jennifer Rexford (Princeton) CS 4226:

More information

A Study of Protocols for Low-Latency Video Transport over the Internet

A Study of Protocols for Low-Latency Video Transport over the Internet A Study of Protocols for Low-Latency Video Transort over the Internet Ciro A. Noronha, Ph.D. Cobalt Digital Santa Clara, CA ciro.noronha@cobaltdigital.com Juliana W. Noronha University of California, Davis

More information

An Indexing Framework for Structured P2P Systems

An Indexing Framework for Structured P2P Systems An Indexing Framework for Structured P2P Systems Adina Crainiceanu Prakash Linga Ashwin Machanavajjhala Johannes Gehrke Carl Lagoze Jayavel Shanmugasundaram Deartment of Comuter Science, Cornell University

More information

Software Defined Networking

Software Defined Networking Software Defined Networking Jennifer Rexford COS 461: Computer Networks Lectures: MW 10-10:50am in Architecture N101 http://www.cs.princeton.edu/courses/archive/spr12/cos461/ The Internet: A Remarkable

More information

EP2200 Performance analysis of Communication networks. Topic 3 Congestion and rate control

EP2200 Performance analysis of Communication networks. Topic 3 Congestion and rate control EP00 Performance analysis of Communication networks Toic 3 Congestion and rate control Congestion, rate and error control Lecture material: Bertsekas, Gallager, Data networks, 6.- I. Kay, Stochastic modeling,

More information

has been retired This version of the software Sage Timberline Office Get Started Document Management 9.8 NOTICE

has been retired This version of the software Sage Timberline Office Get Started Document Management 9.8 NOTICE This version of the software has been retired Sage Timberline Office Get Started Document Management 9.8 NOTICE This document and the Sage Timberline Office software may be used only in accordance with

More information

Introduction to Software-Defined Networking UG3 Computer Communications & Networks (COMN)

Introduction to Software-Defined Networking UG3 Computer Communications & Networks (COMN) Introduction to Software-Defined Networking UG3 Computer Communications & Networks (COMN) Myungjin Lee myungjin.lee@ed.ac.uk Courtesy note: Slides from course CPS514 Spring 2013 at Duke University and

More information

10. Multiprocessor Scheduling (Advanced)

10. Multiprocessor Scheduling (Advanced) 10. Multirocessor Scheduling (Advanced) Oerating System: Three Easy Pieces AOS@UC 1 Multirocessor Scheduling The rise of the multicore rocessor is the source of multirocessorscheduling roliferation. w

More information

Cloud Networking (VITMMA02) Software Defined Networking (SDN) in the Cloud

Cloud Networking (VITMMA02) Software Defined Networking (SDN) in the Cloud Cloud Networking (VITMMA02) Software Defined Networking (SDN) in the Cloud Markosz Maliosz PhD Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Traditional

More information

Software Defined Networks

Software Defined Networks Software Defined Networks A quick overview Based primarily on the presentations of Prof. Scott Shenker of UC Berkeley The Future of Networking, and the Past of Protocols Please watch the YouTube video

More information

Layered Switching for Networks on Chip

Layered Switching for Networks on Chip Layered Switching for Networks on Chi Zhonghai Lu zhonghai@kth.se Ming Liu mingliu@kth.se Royal Institute of Technology, Sweden Axel Jantsch axel@kth.se ABSTRACT We resent and evaluate a novel switching

More information

Taxonomy of SDN. Vara Varavithya 17 January 2018

Taxonomy of SDN. Vara Varavithya 17 January 2018 Taxonomy of SDN Vara Varavithya 17 January 2018 Modern Data Center Environmentally protected warehouses Large number of computers for compute and storage Blades Computer- Top-of-Rack (TOR) Switches Full

More information

Autonomic Physical Database Design - From Indexing to Multidimensional Clustering

Autonomic Physical Database Design - From Indexing to Multidimensional Clustering Autonomic Physical Database Design - From Indexing to Multidimensional Clustering Stehan Baumann, Kai-Uwe Sattler Databases and Information Systems Grou Technische Universität Ilmenau, Ilmenau, Germany

More information

Shuigeng Zhou. May 18, 2016 School of Computer Science Fudan University

Shuigeng Zhou. May 18, 2016 School of Computer Science Fudan University Query Processing Shuigeng Zhou May 18, 2016 School of Comuter Science Fudan University Overview Outline Measures of Query Cost Selection Oeration Sorting Join Oeration Other Oerations Evaluation of Exressions

More information

The VEGA Moderately Parallel MIMD, Moderately Parallel SIMD, Architecture for High Performance Array Signal Processing

The VEGA Moderately Parallel MIMD, Moderately Parallel SIMD, Architecture for High Performance Array Signal Processing The VEGA Moderately Parallel MIMD, Moderately Parallel SIMD, Architecture for High Performance Array Signal Processing Mikael Taveniku 2,3, Anders Åhlander 1,3, Magnus Jonsson 1 and Bertil Svensson 1,2

More information

22. Swaping: Policies

22. Swaping: Policies 22. Swaing: Policies Oerating System: Three Easy Pieces 1 Beyond Physical Memory: Policies Memory ressure forces the OS to start aging out ages to make room for actively-used ages. Deciding which age to

More information

1.5 Case Study. dynamic connectivity quick find quick union improvements applications

1.5 Case Study. dynamic connectivity quick find quick union improvements applications . Case Study dynamic connectivity quick find quick union imrovements alications Subtext of today s lecture (and this course) Stes to develoing a usable algorithm. Model the roblem. Find an algorithm to

More information

BGP Path visibility issues.

BGP Path visibility issues. BGP Path visibility issues Pierre.Francois@UCLouvain.be ToC ibgp draft-ietf-idr-add-aths Why doing Add-aths draft-ietf-idr-add-aths-guidelines (draft-uttaro-idr-add-aths-guidelines) Why only a small subset

More information

Chapter 5 Network Layer: The Control Plane

Chapter 5 Network Layer: The Control Plane Chapter 5 Network Layer: The Control Plane A note on the use of these Powerpoint slides: We re making these slides freely available to all (faculty, students, readers). They re in PowerPoint form so you

More information

2. Introduction to Operating Systems

2. Introduction to Operating Systems 2. Introduction to Oerating Systems Oerating System: Three Easy Pieces 1 What a haens when a rogram runs? A running rogram executes instructions. 1. The rocessor fetches an instruction from memory. 2.

More information

Skip List Based Authenticated Data Structure in DAS Paradigm

Skip List Based Authenticated Data Structure in DAS Paradigm 009 Eighth International Conference on Grid and Cooerative Comuting Ski List Based Authenticated Data Structure in DAS Paradigm Jieing Wang,, Xiaoyong Du,. Key Laboratory of Data Engineering and Knowledge

More information

10. Parallel Methods for Data Sorting

10. Parallel Methods for Data Sorting 10. Parallel Methods for Data Sorting 10. Parallel Methods for Data Sorting... 1 10.1. Parallelizing Princiles... 10.. Scaling Parallel Comutations... 10.3. Bubble Sort...3 10.3.1. Sequential Algorithm...3

More information

SIMULATION SYSTEM MODELING FOR MASS CUSTOMIZATION MANUFACTURING

SIMULATION SYSTEM MODELING FOR MASS CUSTOMIZATION MANUFACTURING Proceedings of the 2002 Winter Simulation Conference E. Yücesan, C.-H. Chen, J. L. Snowdon, and J. M. Charnes, eds.. SIMULATION SYSTEM MODELING FOR MASS CUSTOMIATION MANUFACTURING Guixiu Qiao Charles McLean

More information

Optimizing Dynamic Memory Management!

Optimizing Dynamic Memory Management! Otimizing Dynamic Memory Management! 1 Goals of this Lecture! Hel you learn about:" Details of K&R hea mgr" Hea mgr otimizations related to Assignment #6" Faster free() via doubly-linked list, redundant

More information

The Anubis Service. Paul Murray Internet Systems and Storage Laboratory HP Laboratories Bristol HPL June 8, 2005*

The Anubis Service. Paul Murray Internet Systems and Storage Laboratory HP Laboratories Bristol HPL June 8, 2005* The Anubis Service Paul Murray Internet Systems and Storage Laboratory HP Laboratories Bristol HPL-2005-72 June 8, 2005* timed model, state monitoring, failure detection, network artition Anubis is a fully

More information

SEARCH ENGINE MANAGEMENT

SEARCH ENGINE MANAGEMENT e-issn 2455 1392 Volume 2 Issue 5, May 2016. 254 259 Scientific Journal Imact Factor : 3.468 htt://www.ijcter.com SEARCH ENGINE MANAGEMENT Abhinav Sinha Kalinga Institute of Industrial Technology, Bhubaneswar,

More information

Distributed Systems (5DV147)

Distributed Systems (5DV147) Distributed Systems (5DV147) Mutual Exclusion and Elections Fall 2013 1 Processes often need to coordinate their actions Which rocess gets to access a shared resource? Has the master crashed? Elect a new

More information

Argo Programming Guide

Argo Programming Guide Argo Programming Guide Evangelia Kasaaki, asmus Bo Sørensen February 9, 2015 Coyright 2014 Technical University of Denmark This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International

More information

OMNI: An Efficient Overlay Multicast. Infrastructure for Real-time Applications

OMNI: An Efficient Overlay Multicast. Infrastructure for Real-time Applications OMNI: An Efficient Overlay Multicast Infrastructure for Real-time Alications Suman Banerjee, Christoher Kommareddy, Koushik Kar, Bobby Bhattacharjee, Samir Khuller Abstract We consider an overlay architecture

More information

CASCH - a Scheduling Algorithm for "High Level"-Synthesis

CASCH - a Scheduling Algorithm for High Level-Synthesis CASCH a Scheduling Algorithm for "High Level"Synthesis P. Gutberlet H. Krämer W. Rosenstiel Comuter Science Research Center at the University of Karlsruhe (FZI) HaidundNeuStr. 1014, 7500 Karlsruhe, F.R.G.

More information

Design Trade-offs in Customized On-chip Crossbar Schedulers

Design Trade-offs in Customized On-chip Crossbar Schedulers J Sign Process Syst () 8:9 8 DOI.7/s-8--x Design Trade-offs in Customized On-chi Crossbar Schedulers Jae Young Hur Stehan Wong Todor Stefanov Received: October 7 / Revised: June 8 / cceted: ugust 8 / Published

More information

Statistical Detection for Network Flooding Attacks

Statistical Detection for Network Flooding Attacks Statistical Detection for Network Flooding Attacks C. S. Chao, Y. S. Chen, and A.C. Liu Det. of Information Engineering, Feng Chia Univ., Taiwan 407, OC. Email: cschao@fcu.edu.tw Abstract In order to meet

More information

An Efficient Video Program Delivery algorithm in Tree Networks*

An Efficient Video Program Delivery algorithm in Tree Networks* 3rd International Symosium on Parallel Architectures, Algorithms and Programming An Efficient Video Program Delivery algorithm in Tree Networks* Fenghang Yin 1 Hong Shen 1,2,** 1 Deartment of Comuter Science,

More information

Identity-sensitive Points-to Analysis for the Dynamic Behavior of JavaScript Objects

Identity-sensitive Points-to Analysis for the Dynamic Behavior of JavaScript Objects Identity-sensitive Points-to Analysis for the Dynamic Behavior of JavaScrit Objects Shiyi Wei and Barbara G. Ryder Deartment of Comuter Science, Virginia Tech, Blacksburg, VA, USA. {wei,ryder}@cs.vt.edu

More information

Matlab Virtual Reality Simulations for optimizations and rapid prototyping of flexible lines systems

Matlab Virtual Reality Simulations for optimizations and rapid prototyping of flexible lines systems Matlab Virtual Reality Simulations for otimizations and raid rototying of flexible lines systems VAMVU PETRE, BARBU CAMELIA, POP MARIA Deartment of Automation, Comuters, Electrical Engineering and Energetics

More information

Implementation of Evolvable Fuzzy Hardware for Packet Scheduling Through Online Context Switching

Implementation of Evolvable Fuzzy Hardware for Packet Scheduling Through Online Context Switching Imlementation of Evolvable Fuzzy Hardware for Packet Scheduling Through Online Context Switching Ju Hui Li, eng Hiot Lim and Qi Cao School of EEE, Block S Nanyang Technological University Singaore 639798

More information

A Petri net-based Approach to QoS-aware Configuration for Web Services

A Petri net-based Approach to QoS-aware Configuration for Web Services A Petri net-based Aroach to QoS-aware Configuration for Web s PengCheng Xiong, YuShun Fan and MengChu Zhou, Fellow, IEEE Abstract With the develoment of enterrise-wide and cross-enterrise alication integration

More information

IMS Network Deployment Cost Optimization Based on Flow-Based Traffic Model

IMS Network Deployment Cost Optimization Based on Flow-Based Traffic Model IMS Network Deloyment Cost Otimization Based on Flow-Based Traffic Model Jie Xiao, Changcheng Huang and James Yan Deartment of Systems and Comuter Engineering, Carleton University, Ottawa, Canada {jiexiao,

More information

42. Crash Consistency: FSCK and Journaling

42. Crash Consistency: FSCK and Journaling 42. Crash Consistency: FSCK and Journaling Oerating System: Three Easy Pieces AOS@UC 1 Crash Consistency AOS@UC 2 Crash Consistency Unlike most data structure, file system data structures must ersist w

More information

Recap: Consensus. CSE 486/586 Distributed Systems Mutual Exclusion. Why Mutual Exclusion? Why Mutual Exclusion? Mutexes. Mutual Exclusion C 1

Recap: Consensus. CSE 486/586 Distributed Systems Mutual Exclusion. Why Mutual Exclusion? Why Mutual Exclusion? Mutexes. Mutual Exclusion C 1 Reca: Consensus Distributed Systems Mutual Exclusion Steve Ko Comuter Sciences and Engineering University at Buffalo On a synchronous system There s an algorithm that works. On an asynchronous system It

More information

CS-580K/480K Advanced Topics in Cloud Computing. Software-Defined Networking

CS-580K/480K Advanced Topics in Cloud Computing. Software-Defined Networking CS-580K/480K Advanced Topics in Cloud Computing Software-Defined Networking 1 An Innovation from Stanford Nick McKeown In 2006, OpenFlow is proposed, which provides an open protocol to program the flow-table

More information

Simulating Ocean Currents. Simulating Galaxy Evolution

Simulating Ocean Currents. Simulating Galaxy Evolution Simulating Ocean Currents (a) Cross sections (b) Satial discretization of a cross section Model as two-dimensional grids Discretize in sace and time finer satial and temoral resolution => greater accuracy

More information

Equality-Based Translation Validator for LLVM

Equality-Based Translation Validator for LLVM Equality-Based Translation Validator for LLVM Michael Ste, Ross Tate, and Sorin Lerner University of California, San Diego {mste,rtate,lerner@cs.ucsd.edu Abstract. We udated our Peggy tool, reviously resented

More information

This version of the software

This version of the software Sage Estimating (SQL) (formerly Sage Timberline Estimating) SQL Server Guide Version 16.11 This is a ublication of Sage Software, Inc. 2015 The Sage Grou lc or its licensors. All rights reserved. Sage,

More information

Lecture 18. Today, we will discuss developing algorithms for a basic model for parallel computing the Parallel Random Access Machine (PRAM) model.

Lecture 18. Today, we will discuss developing algorithms for a basic model for parallel computing the Parallel Random Access Machine (PRAM) model. U.C. Berkeley CS273: Parallel and Distributed Theory Lecture 18 Professor Satish Rao Lecturer: Satish Rao Last revised Scribe so far: Satish Rao (following revious lecture notes quite closely. Lecture

More information

MSO Exam January , 17:00 20:00

MSO Exam January , 17:00 20:00 MSO 2014 2015 Exam January 26 2015, 17:00 20:00 Name: Student number: Please read the following instructions carefully: Fill in your name and student number above. Be reared to identify yourself with your

More information

Sensitivity Analysis for an Optimal Routing Policy in an Ad Hoc Wireless Network

Sensitivity Analysis for an Optimal Routing Policy in an Ad Hoc Wireless Network 1 Sensitivity Analysis for an Otimal Routing Policy in an Ad Hoc Wireless Network Tara Javidi and Demosthenis Teneketzis Deartment of Electrical Engineering and Comuter Science University of Michigan Ann

More information

Sage Estimating. (formerly Sage Timberline Estimating) Getting Started Guide

Sage Estimating. (formerly Sage Timberline Estimating) Getting Started Guide Sage Estimating (formerly Sage Timberline Estimating) Getting Started Guide This is a ublication of Sage Software, Inc. Document Number 20001S14030111ER 09/2012 2012 Sage Software, Inc. All rights reserved.

More information

An Efficient Coding Method for Coding Region-of-Interest Locations in AVS2

An Efficient Coding Method for Coding Region-of-Interest Locations in AVS2 An Efficient Coding Method for Coding Region-of-Interest Locations in AVS2 Mingliang Chen 1, Weiyao Lin 1*, Xiaozhen Zheng 2 1 Deartment of Electronic Engineering, Shanghai Jiao Tong University, China

More information

A New and Efficient Algorithm-Based Fault Tolerance Scheme for A Million Way Parallelism

A New and Efficient Algorithm-Based Fault Tolerance Scheme for A Million Way Parallelism A New and Efficient Algorithm-Based Fault Tolerance Scheme for A Million Way Parallelism Erlin Yao, Mingyu Chen, Rui Wang, Wenli Zhang, Guangming Tan Key Laboratory of Comuter System and Architecture Institute

More information

Sage Estimating (formerly Sage Timberline Estimating) Getting Started Guide. Version has been retired. This version of the software

Sage Estimating (formerly Sage Timberline Estimating) Getting Started Guide. Version has been retired. This version of the software Sage Estimating (formerly Sage Timberline Estimating) Getting Started Guide Version 14.12 This version of the software has been retired This is a ublication of Sage Software, Inc. Coyright 2014. Sage Software,

More information

Space-efficient Region Filling in Raster Graphics

Space-efficient Region Filling in Raster Graphics "The Visual Comuter: An International Journal of Comuter Grahics" (submitted July 13, 1992; revised December 7, 1992; acceted in Aril 16, 1993) Sace-efficient Region Filling in Raster Grahics Dominik Henrich

More information

Network Layer: The Control Plane

Network Layer: The Control Plane Network Layer: The Control Plane 7 th Edition, Global Edition Jim Kurose, Keith Ross Pearson April 06 5- Software defined networking (SDN) Internet network layer: historically has been implemented via

More information

Efficient Processing of Top-k Dominating Queries on Multi-Dimensional Data

Efficient Processing of Top-k Dominating Queries on Multi-Dimensional Data Efficient Processing of To-k Dominating Queries on Multi-Dimensional Data Man Lung Yiu Deartment of Comuter Science Aalborg University DK-922 Aalborg, Denmark mly@cs.aau.dk Nikos Mamoulis Deartment of

More information

mswitch: A Highly-Scalable, Modular Software Switch

mswitch: A Highly-Scalable, Modular Software Switch mswitch: A Highly-Scalable, Modular Software Switch Michio Honda, Felie Huici, Giusee Lettieri, Luigi Rizzo NetA Inc., NEC Euroe Ltd., Universita di Pisa michio@neta.com, felie.huici@neclab.eu, {g.lettieri,rizzo}@iet.unii.it

More information

So#ware Defined Networks and OpenFlow

So#ware Defined Networks and OpenFlow So#ware Defined Networks and OpenFlow NANOG 50, October 2010 Nick McKeown nickm@stanford.edu With Martin Casado and Scott Shenker And contributions from many others Supported by NSF, Stanford Clean Slate

More information

Election Algorithms. has elected i. will eventually set elected i

Election Algorithms. has elected i. will eventually set elected i Election Algorithms Election 8 algorithm designed to designate one unique rocess out of a set of rocesses with similar caabilities to take over certain functions in a distributes system central server

More information

GENERIC PILOT AND FLIGHT CONTROL MODEL FOR USE IN SIMULATION STUDIES

GENERIC PILOT AND FLIGHT CONTROL MODEL FOR USE IN SIMULATION STUDIES AIAA Modeling and Simulation Technologies Conference and Exhibit 5-8 August 22, Monterey, California AIAA 22-4694 GENERIC PILOT AND FLIGHT CONTROL MODEL FOR USE IN SIMULATION STUDIES Eric N. Johnson *

More information

Introduction to Parallel Algorithms

Introduction to Parallel Algorithms CS 1762 Fall, 2011 1 Introduction to Parallel Algorithms Introduction to Parallel Algorithms ECE 1762 Algorithms and Data Structures Fall Semester, 2011 1 Preliminaries Since the early 1990s, there has

More information

Virtualized PE for BGP/MPLS L3-VPN using Open-Source Software

Virtualized PE for BGP/MPLS L3-VPN using Open-Source Software Virtualized PE for BGP/MPLS L3-VPN using Oen-Source Software NANOG 74 (October 2018) Bilal Anwer, Robert Bays, Vijay Goalakrishnan, Bo Han, Dewi Morgan, Patrick Ruddy, Aman Shaikh, Susheela Vaidya, Chengwei

More information

Signature File Hierarchies and Signature Graphs: a New Index Method for Object-Oriented Databases

Signature File Hierarchies and Signature Graphs: a New Index Method for Object-Oriented Databases Signature File Hierarchies and Signature Grahs: a New Index Method for Object-Oriented Databases Yangjun Chen* and Yibin Chen Det. of Business Comuting University of Winnieg, Manitoba, Canada R3B 2E9 ABSTRACT

More information

Using Standard AADL for COMPASS

Using Standard AADL for COMPASS Using Standard AADL for COMPASS (noll@cs.rwth-aachen.de) AADL Standards Meeting Aachen, Germany; July 5 8, 06 Overview Introduction SLIM Language Udates COMPASS Develoment Roadma Fault Injections Parametric

More information

Software-Defined Networking (Continued)

Software-Defined Networking (Continued) Software-Defined Networking (Continued) CS640, 2015-04-23 Announcements Assign #5 released due Thursday, May 7 at 11pm Outline Recap SDN Stack Layer 2 Learning Switch Control Application Design Considerations

More information

Lecture 8: Orthogonal Range Searching

Lecture 8: Orthogonal Range Searching CPS234 Comutational Geometry Setember 22nd, 2005 Lecture 8: Orthogonal Range Searching Lecturer: Pankaj K. Agarwal Scribe: Mason F. Matthews 8.1 Range Searching The general roblem of range searching is

More information

IEEE High Performance Serial Bus

IEEE High Performance Serial Bus IEEE 1394-1995 High Performance Serial Bus Michael D. Johas Teener Editor, P1394 Working Grou Plumbing Architect, Ale Comuter, Inc. One Infinite Loo, MS 35-OEM Cuertino, CA 95014 teener@ale.com Background

More information

Chapter 5 Network Layer: The Control Plane

Chapter 5 Network Layer: The Control Plane Chapter 5 Network Layer: The Control Plane A note on the use of these Powerpoint slides: We re making these slides freely available to all (faculty, students, readers). They re in PowerPoint form so you

More information

Sage Document Management Version 17.1

Sage Document Management Version 17.1 Sage Document Management Version 17.1 User's Guide This is a ublication of Sage Software, Inc. 2017 The Sage Grou lc or its licensors. All rights reserved. Sage, Sage logos, and Sage roduct and service

More information

32. Common Concurrency Problems.

32. Common Concurrency Problems. 32. Common Concurrency Problems. Oerating System: Three Easy Pieces AOS@UC 1 Common Concurrency Problems More recent work focuses on studying other tyes of common concurrency bugs. w Take a brief look

More information

Compiling for Heterogeneous Systems: A Survey and an. Approach

Compiling for Heterogeneous Systems: A Survey and an. Approach Comiling for Heterogeneous Systems: A Survey and an Aroach Kathryn S. McKinley, J. Eliot B. Moss, Sharad K. Singhai, Glen E. Weaver, Charles C. Weems CMPSCI Techincal Reort 95-59 Setember 1995 Deartment

More information

Simulation Modelling Practice and Theory

Simulation Modelling Practice and Theory Simulation Modelling Practice and Theory 19 (2011) 494 515 Contents lists available at ScienceDirect Simulation Modelling Practice and Theory journal homeage: www.elsevier.com/locate/simat Simulating and

More information

CENTRAL AND PARALLEL PROJECTIONS OF REGULAR SURFACES: GEOMETRIC CONSTRUCTIONS USING 3D MODELING SOFTWARE

CENTRAL AND PARALLEL PROJECTIONS OF REGULAR SURFACES: GEOMETRIC CONSTRUCTIONS USING 3D MODELING SOFTWARE CENTRAL AND PARALLEL PROJECTIONS OF REGULAR SURFACES: GEOMETRIC CONSTRUCTIONS USING 3D MODELING SOFTWARE Petra Surynková Charles University in Prague, Faculty of Mathematics and Physics, Sokolovská 83,

More information

Optimization of Collective Communication Operations in MPICH

Optimization of Collective Communication Operations in MPICH To be ublished in the International Journal of High Performance Comuting Alications, 5. c Sage Publications. Otimization of Collective Communication Oerations in MPICH Rajeev Thakur Rolf Rabenseifner William

More information

Protecting Mobile Agents against Malicious Host Attacks Using Threat Diagnostic AND/OR Tree

Protecting Mobile Agents against Malicious Host Attacks Using Threat Diagnostic AND/OR Tree Protecting Mobile Agents against Malicious Host Attacks Using Threat Diagnostic AND/OR Tree Magdy Saeb, Meer Hamza, Ashraf Soliman. Arab Academy for Science, Technology & Maritime Transort Comuter Engineering

More information

Lecture 2: Fixed-Radius Near Neighbors and Geometric Basics

Lecture 2: Fixed-Radius Near Neighbors and Geometric Basics structure arises in many alications of geometry. The dual structure, called a Delaunay triangulation also has many interesting roerties. Figure 3: Voronoi diagram and Delaunay triangulation. Search: Geometric

More information

SPITFIRE: Scalable Parallel Algorithms for Test Set Partitioned Fault Simulation

SPITFIRE: Scalable Parallel Algorithms for Test Set Partitioned Fault Simulation To aear in IEEE VLSI Test Symosium, 1997 SITFIRE: Scalable arallel Algorithms for Test Set artitioned Fault Simulation Dili Krishnaswamy y Elizabeth M. Rudnick y Janak H. atel y rithviraj Banerjee z y

More information

Models for Advancing PRAM and Other Algorithms into Parallel Programs for a PRAM-On-Chip Platform

Models for Advancing PRAM and Other Algorithms into Parallel Programs for a PRAM-On-Chip Platform Models for Advancing PRAM and Other Algorithms into Parallel Programs for a PRAM-On-Chi Platform Uzi Vishkin George C. Caragea Bryant Lee Aril 2006 University of Maryland, College Park, MD 20740 UMIACS-TR

More information

An Efficient End-to-End QoS supporting Algorithm in NGN Using Optimal Flows and Measurement Feed-back for Ubiquitous and Distributed Applications

An Efficient End-to-End QoS supporting Algorithm in NGN Using Optimal Flows and Measurement Feed-back for Ubiquitous and Distributed Applications An Efficient End-to-End QoS suorting Algorithm in NGN Using Otimal Flows and Measurement Feed-back for Ubiquitous and Distributed Alications Se Youn Ban, Seong Gon Choi 2, Jun Kyun Choi Information and

More information

CSC 401 Data and Computer Communications Networks

CSC 401 Data and Computer Communications Networks CSC 401 Data and Computer Communications Networks Network Layer ICMP (5.6), Network Management(5.7) & SDN (5.1, 5.5, 4.4) Prof. Lina Battestilli Fall 2017 Outline 5.6 ICMP: The Internet Control Message

More information

So#ware Defined Networking

So#ware Defined Networking The Internet: A Remarkable Story 2! Tremendous success From research experiment to global infrastructure So#ware Defined Networking Brilliance of under- specifying Network: best- effort packet delivery

More information

Object and Native Code Thread Mobility Among Heterogeneous Computers

Object and Native Code Thread Mobility Among Heterogeneous Computers Object and Native Code Thread Mobility Among Heterogeneous Comuters Bjarne Steensgaard Eric Jul Microsoft Research DIKU (Det. of Comuter Science) One Microsoft Way University of Coenhagen Redmond, WA 98052

More information

Randomized algorithms: Two examples and Yao s Minimax Principle

Randomized algorithms: Two examples and Yao s Minimax Principle Randomized algorithms: Two examles and Yao s Minimax Princile Maximum Satisfiability Consider the roblem Maximum Satisfiability (MAX-SAT). Bring your knowledge u-to-date on the Satisfiability roblem. Maximum

More information

虛擬化技術 Virtualization Techniques

虛擬化技術 Virtualization Techniques 虛擬化技術 Virtualization Techniques Network Virtualization Software Defined Network Introduction Motivation Concept Open Flow Virtual Switch SOFTWARE DEFINED NETWORK We have lost our way Routing, management,

More information

Mitigating the Impact of Decompression Latency in L1 Compressed Data Caches via Prefetching

Mitigating the Impact of Decompression Latency in L1 Compressed Data Caches via Prefetching Mitigating the Imact of Decomression Latency in L1 Comressed Data Caches via Prefetching by Sean Rea A thesis resented to Lakehead University in artial fulfillment of the requirement for the degree of

More information

Multicast in Wormhole-Switched Torus Networks using Edge-Disjoint Spanning Trees 1

Multicast in Wormhole-Switched Torus Networks using Edge-Disjoint Spanning Trees 1 Multicast in Wormhole-Switched Torus Networks using Edge-Disjoint Sanning Trees 1 Honge Wang y and Douglas M. Blough z y Myricom Inc., 325 N. Santa Anita Ave., Arcadia, CA 916, z School of Electrical and

More information

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article. Robot vision system design and implementation based on Open CV

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article. Robot vision system design and implementation based on Open CV Available online www.jocr.com Journal of Chemical and Pharmaceutical Research, 3, 5():68-689 Research Article ISSN : 975-7384 CODEN(USA) : JCPRC5 Robot vision system design and imlementation based on Oen

More information

PA-NEMO: Proxy Mobile IPv6-aided Network Mobility Management Scheme for 6LoWPAN

PA-NEMO: Proxy Mobile IPv6-aided Network Mobility Management Scheme for 6LoWPAN htt://dx.doi.org/10.5755/j01.eee.20.3.3951 ELEKRONIKA IR ELEKROENIKA, ISSN 1392-1215, VOL. 20, NO. 3, 2014 PA-NEMO: Proxy Mobile IPv6-aided Network Mobility Management Scheme for 6LoWPAN Ke Xiong 1, Yu

More information

EE678 Application Presentation Content Based Image Retrieval Using Wavelets

EE678 Application Presentation Content Based Image Retrieval Using Wavelets EE678 Alication Presentation Content Based Image Retrieval Using Wavelets Grou Members: Megha Pandey megha@ee. iitb.ac.in 02d07006 Gaurav Boob gb@ee.iitb.ac.in 02d07008 Abstract: We focus here on an effective

More information

COMP Parallel Computing. BSP (1) Bulk-Synchronous Processing Model

COMP Parallel Computing. BSP (1) Bulk-Synchronous Processing Model COMP 6 - Parallel Comuting Lecture 6 November, 8 Bulk-Synchronous essing Model Models of arallel comutation Shared-memory model Imlicit communication algorithm design and analysis relatively simle but

More information

An improved algorithm for Hausdorff Voronoi diagram for non-crossing sets

An improved algorithm for Hausdorff Voronoi diagram for non-crossing sets An imroved algorithm for Hausdorff Voronoi diagram for non-crossing sets Frank Dehne, Anil Maheshwari and Ryan Taylor May 26, 2006 Abstract We resent an imroved algorithm for building a Hausdorff Voronoi

More information